XDMOD

Prerequisits

This example use python API for XDMoD analytic framework. So you already need to have installed python version. In R you should install reticulate library and bound the python with XDMoD framework.

Quick Conda Install

Here is a quick tip on installation (tested in WSL ubuntu)

conda install requests
conda create -n xdmod-notebooks -y python=3.11 r=4.3
conda activate xdmod-notebooks
# base-notebook
conda install -y 'jupyterlab' 'notebook' 'jupyterhub' 'nbclassic'
# scipy-notebook
conda install -y  'altair' 'beautifulsoup4' 'bokeh' 'bottleneck' 'cloudpickle' \
    'conda-forge::blas=*=openblas' \
    'cython' 'dask' 'dill' 'h5py' 'ipympl' 'ipywidgets' 'jupyterlab-git' \
    'matplotlib-base' 'numba' 'numexpr' 'openpyxl' 'pandas' 'patsy' 'protobuf' \
    'pytables' 'scikit-image' 'scikit-learn' 'scipy' 'seaborn' 'sqlalchemy' \
    'statsmodels' 'sympy' 'widgetsnbextension' 'xlrd'
# r-notebook
conda install -y 'r-base' 'r-caret' 'r-crayon' 'r-devtools' 'r-e1071' \
    'r-forecast' 'r-hexbin' 'r-htmltools' 'r-htmlwidgets' 'r-irkernel' \
    'r-nycflights13' 'r-randomforest' 'r-rcurl' 'r-rmarkdown' 'r-rodbc' \
    'r-rsqlite' 'r-shiny' 'r-tidymodels' 'r-tidyverse' 'unixodbc'

# Other
conda install -y 'pymysql' 'requests' \
    'r-plotly' 'r-repr' 'r-irdisplay' 'r-pbdzmq' 'r-reticulate' 'r-cowplot' \
    'r-rjson' 'r-dotenv'
    
# Install xdmod-data
pip install --upgrade 'xdmod-data>=1.0.0,<2.0.0' python-dotenv tabulate

# Install rstudio server
wget -q "https://download2.rstudio.org/server/jammy/amd64/rstudio-server-2023.12.1-402-amd64.deb"
dpkg -i rstudio-server-*-amd64.deb
rm rstudio-server-*-amd64.deb

# specify which version of r to use
echo "rsession-which-r=$(which R)" | sudo tee -a /etc/rstudio/rserver.conf

The first time rstudio server will be started on following times start is as:

# to start rserver:
sudo /usr/lib/rstudio-server/bin/rserver

Setup

knitr::opts_chunk$set(echo = TRUE)

library(dotenv)
library(reticulate)
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.3     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.3     ✔ tibble    3.2.1
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(plotly)

## 
## Attaching package: 'plotly'
## 
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## 
## The following object is masked from 'package:stats':
## 
##     filter
## 
## The following object is masked from 'package:graphics':
## 
##     layout

library(knitr)
library(rmarkdown)

# replace xdmod-notebooks with conda enviroment for python to use
use_condaenv("xdmod-notebooks")
# on windows ~ points to Documents
load_dot_env(path.expand("~/xdmod-data.env"))

Use XDMoD Analytical Framework as Python API

Using python chunks

# This is a python chunk
# Initialize the XDMoD Data Warehouse
from xdmod_data.warehouse import DataWarehouse
dw = DataWarehouse('https://xdmod.access-ci.org')

# This is a python chunk
# Get data
with dw:
    data = dw.get_data(
        duration=('2023-01-01', '2023-04-30'),
        realm='Jobs',
        metric='Number of Users: Active',
    )

# Use data in R
df <- py$data %>% 
    rownames_to_column(var="Time") %>% # Move row names to column
    tibble() %>% # use newer data.frame
    mutate(Time=ymd(Time)) # convert character to date

df %>% paged_table()

# plot
ggplotly(
    ggplot(df, aes(x=Time,y=`Number of Users: Active`)) +
        geom_line()
)

Calling from R using reticulate

# Initialize the XDMoD Data Warehouse
warehouse <- import("xdmod_data.warehouse")
dw <- warehouse$DataWarehouse('https://xdmod.access-ci.org')

# Initialize the XDMoD Data Warehouse
with(dw,{
    data2 <- dw$get_data(
        duration=c('2023-01-01', '2023-04-30'),
        realm='Jobs',
        metric='Number of Users: Active',
)})

# Use data in R
df2 <-data2 %>% 
    rownames_to_column(var="Time") %>% # Move row names to column
    tibble() %>% # use newer data.frame
    mutate(Time=ymd(Time)) # convert character to date

df2 %>% paged_table()

# plot
ggplotly(
    ggplot(df2, aes(x=Time,y=`Number of Users: Active`)) +
        geom_line()
)